{"id":27731,"date":"2026-05-26T15:03:37","date_gmt":"2026-05-26T15:03:37","guid":{"rendered":"https:\/\/www.qureca.com\/?post_type=tribe_events&p=27731"},"modified":"2026-05-26T15:03:37","modified_gmt":"2026-05-26T15:03:37","slug":"beyond-classical-ai-quantum-machine-learning-for-anomaly-detection-across-industries","status":"publish","type":"tribe_events","link":"https:\/\/www.qureca.com\/fr\/calendar\/beyond-classical-ai-quantum-machine-learning-for-anomaly-detection-across-industries\/","title":{"rendered":"Beyond Classical AI: Quantum Machine Learning for Anomaly Detection Across Industries"},"content":{"rendered":"

Anomaly detection is one of the most critical challenges across industries, from identifying equipment faults on a factory floor to flagging fraudulent transactions in financial services or detecting irregularities in medical diagnostics. But as data complexity grows and the cost of missed anomalies rises, classical AI is beginning to show its limits.<\/p>\n

Quantum Machine Learning offers a fundamentally different approach. In collaboration with\u00a0<\/span>Fraunhofer ITWM<\/strong>,\u00a0<\/span>WISER\u00a0<\/span><\/strong>developed and benchmarked Quantum Neural Networks (QNNs) on real industrial data, training models on sensor readings from pneumatic systems and rotating machinery to detect faults before they escalate. Our benchmark evaluates a range of encoding strategies and circuit configurations, providing an assessment of the current practical performance of QML methods.<\/p>\n

This session uses industrial defect detection as a test case, but the core principles and model architectures apply directly to anomaly detection across many sectors, including financial services (fraud and market surveillance), healthcare (diagnostic and drug quality issues), energy (grid faults and predictive maintenance), logistics (supply\u2011chain disruptions), and cybersecurity (network intrusions and threat patterns).<\/p>\n

In this session, you will:<\/p>\n